Jailbreak Distillation: Renewable Safety Benchmarking.
Jingyu Zhang, Ahmed Elgohary, Xiawei Wang, A S. M. Iftekhar, Ahmed Magooda, Benjamin Van Durme, Daniel Khashabi, Kyle Jackson
Browse the full EMNLP paper archive.
Jingyu Zhang, Ahmed Elgohary, Xiawei Wang, A S. M. Iftekhar, Ahmed Magooda, Benjamin Van Durme, Daniel Khashabi, Kyle Jackson
Browse the full EMNLP paper archive.